Diagnosis-specific readmission risk prediction using electronic health data: a retrospective cohort study

Hebert, Courtney; Shivade, Chaitanya; Foraker, Randi E.; Wasserman, Jared R.; Roth, Caryn; Mekhjian, Hagop S.; Lemeshow, Stanley; Embí, Peter J.

doi:10.1186/1472-6947-14-65

Cited by 55 publications

(57 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of 992 titles identified by our search algorithm, 91 qualified for abstract review, 12 for full-text review, and 7 met our inclusion criteria (Figure 1) (11)(12)(13)(14)(15)(16)(17). Of the seven included studies, 11 unique riskprediction models were tested.…”

Section: Resultsmentioning

confidence: 99%

“…The CMS Pneumonia Administrative Model was the most commonly studied-validated in five separate cohorts (12,14,15). The objective of eight of the models was to identify patients hospitalized for pneumonia at high risk for readmission for potential intervention (11,13,16,17), whereas for three of the models the objective was to estimate hospital-level risk-adjusted 30-day SYSTEMATIC REVIEW readmission rates for the purpose of hospital profiling (12,14,15).…”

Section: Resultsmentioning

confidence: 99%

“…Notably, the addition of census tract-level socioeconomic data to the CMS Pneumonia Administrative Model did not improve model discrimination (C statistic of 0.72 for both) (14). Risk prediction models derived using more clinically granular data (i.e., laboratory results and vital signs) than administrative claims data did not necessarily have better discrimination, with C statistics ranging from 0.59 to 0.67 for all-cause readmission (13,16,17).…”

Section: Model Performancementioning

confidence: 99%

See 2 more Smart Citations

Predicting the Risk of Readmission in Pneumonia. A Systematic Review of Model Performance

Weinreich¹,

Nguyen²,

Wang³

et al. 2016

Annals ATS

View full text Add to dashboard Cite

Rationale: Predicting which patients are at highest risk for readmission after hospitalization for pneumonia could enable hospitals to proactively reallocate scarce resources to reduce 30-day readmissions.Objectives: To synthesize the available literature on readmission risk prediction models for adults who are hospitalized because of pneumonia and describe their performance. Methods:We systematically searched Ovid MEDLINE, Embase, The Cochrane Library, and Cumulative Index to Nursing and Allied Health Literature databases from inception through July 2015. We included studies of adults discharged with pneumonia that developed or validated a model that predicted hospital readmission. Two independent reviewers abstracted data and assessed the risk of bias.Measurements and Main Results: Of 992 citations reviewed, 7 studies met inclusion criteria, which included 11 unique risk prediction models. All-cause 30-day readmission rates ranged from 11.8 to 20.8% (median, 17.3%). Model discrimination (C statistic) ranged from 0.59 to 0.77 (median, 0.63) with the highest-quality, best-validated model, the Centers for Medicare and Medicaid Services Pneumonia Administrative Model performing modestly (C Statistic of 0.63 in 4 separate multicenter cohorts). The best performing model (C statistic of 0.77) was a single-site study that lacked internal validation. The models had adequate calibration, with patients predicted as high risk for readmission having a higher average observed readmission rate than those predicted to be low risk. None of the studies included pneumonia illness severity scores, and only one included measures of in-hospital clinical trajectory and stability on discharge, robust predictors of readmission. Conclusions:We found a limited number of validated pneumoniaspecific readmission models, and their predictive ability was modest. To improve predictive accuracy, future models should include measures of pneumonia illness severity, hospital complications, and stability on discharge.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Model Performancementioning

confidence: 99%

See 1 more Smart Citation

Predicting the Risk of Readmission in Pneumonia. A Systematic Review of Model Performance

Weinreich¹,

Nguyen²,

Wang³

et al. 2016

Annals ATS

View full text Add to dashboard Cite

show abstract

“…Multiple studies examining data from the Centers for Medicare & Medicaid Services and from single centers have reported 30-day readmission rates after hospitalization for acute MI ranging from 13.3% to 20.3%. 2,10,[16][17][18] In the Medicare population, the most common cause of 30-day readmission was heart failure. 10 In contrast, in a study with MI patients of all ages in Olmsted County, Minnesota, ischemic heart disease, chest pain, and heart failure were the most common causes of readmission.…”

Section: Discussionmentioning

confidence: 99%

Unplanned Inpatient and Observation Rehospitalizations After Acute Myocardial Infarction

et al. 2016

View full text Add to dashboard Cite

Background— Previous studies examining early readmission after acute myocardial infarction have focused exclusively on inpatient readmissions. However, from a patient’s perspective, any unplanned inpatient or observation rehospitalization after acute myocardial infarction represents a significant event; these unplanned rehospitalizations have not been well characterized. Methods and Results— We examined all patients with acute myocardial infarction treated with percutaneous coronary intervention and discharged alive from 233 hospitals in the Treatment With Adenosine Diphosphate Receptor Inhibitors: Longitudinal Assessment of Treatment Patterns and Events After Acute Coronary Syndrome (TRANSLATE-ACS) study from 2010 to 2012. Our primary outcome was unplanned rehospitalizations (inpatient or observation status) within 30 days after discharge. We identified factors associated with unplanned rehospitalizations using multivariable logistic regression. Among 12 312 patients, 1326 (10.8%) had 1483 unplanned rehospitalizations within 30 days of the index event: 1028 (69.3%) were inpatient readmissions, and 455 (30.7%) were observation stays. The majority of unplanned rehospitalizations (72%) were for cardiovascular reasons. Variation in hospital rates of 30-day unplanned rehospitalization ranged from 5.4% to 20.0%, with a median of 10.7%. After multivariable modeling, the factors most strongly associated with unplanned rehospitalization were baseline quality of life and depression, followed by index hospital length of stay. Conclusions— Early unplanned rehospitalizations are common after acute myocardial infarction, and close to one third were classified as an observation stay. Predischarge and postdischarge assessments of overall, not just cardiovascular, health and strategies to optimize patient functional status may help to reduce unplanned rehospitalizations. Clinical Trial Registration— URL: http://www.clinicaltrials.gov . Unique identifier: NCT01088503.

show abstract

“…10 These variables are frequently not documented in the electronic medical records. 20 With the present study, we aimed to determine the local factors for readmission in order to implement directed interventions to reduce them.…”

Section: Discussion Findingsmentioning

confidence: 99%

Risk Factors for 30-Day Readmissions after Acute Myocardial Infarction

Rodríguez

Acharya

Olson

et al. 2015

ICFJ

View full text Add to dashboard Cite

BackgroundThe hospital readmission rate has been thought to reflect the quality of patient care. Understanding the risk factors for these can guide strategies to reduce them.MethodsRetrospective cohort design that included all the admissions for AMI from October 2011 to September 2014. Primary outcome was 30-day readmission rate. Secondary outcomes were 7-day readmission rate, reasons for readmission and cardiac-related readmission rate. Univariate and multivariate logistic regression were conducted with Hosmer-Lemeshow goodness-of-fit statistics for model calibration and ROC curve for model discrimination.ResultsWe identified 2958 cases of AMI and 334 readmissions (11.3%). The final sample for analysis included 310 readmitted and 652 non-readmitted patients. The principal causes of readmission were cardiac related (42%), followed by respiratory (15%) and gastrointestinal (11%). Separate analysis for the early readmissions showed the same pattern. 42% of the readmissions happened during the first week and 68% in the first 2 weeks after discharge. Median time for readmission was 10 days. Older age, days from admission to catheterization, complete medical therapy at discharge, diabetes, hypertension, stroke, major psychiatric disorders, insurance status, chronic kidney disease and congestive heart failure were independently associated with 30-day readmission. The final multivariate model discriminated well with a ROC of 0.753 (95% CI 0.72-0.79).ConclusionReasons for readmission found in our study were consistent with previous studies. Absolute readmission rates reported in this study were lower than in some prior publications. We present novel and addressable patient risk factors derived from the index admission that can be used to predict readmission.

show abstract

Diagnosis-specific readmission risk prediction using electronic health data: a retrospective cohort study

Cited by 55 publications

References 35 publications

Predicting the Risk of Readmission in Pneumonia. A Systematic Review of Model Performance

Predicting the Risk of Readmission in Pneumonia. A Systematic Review of Model Performance

Unplanned Inpatient and Observation Rehospitalizations After Acute Myocardial Infarction

Risk Factors for 30-Day Readmissions after Acute Myocardial Infarction

Contact Info

Product

Resources

About